© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33639
    Prev
    Next
    INDEX
    Explanations

    atmosphere and atmospheric conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aps
    -0.10
    eri
    -0.09
    çķ´
    -0.09
    apsed
    -0.09
    ye
    -0.09
    isable
    -0.09
    nap
    -0.09
    zos
    -0.09
    è´¨åľ°
    -0.09
    åĪ¶åº¦æĶ¹éĿ©
    -0.08
    POSITIVE LOGITS
    pheric
    0.13
    ials
    0.12
    ively
    0.11
    åĭĥåĭĥ
    0.10
    istic
    0.09
    ä¸ĩåįĥ
    0.09
    ä¸Ģå®ļçļĦ
    0.09
    åĢĻ
    0.09
    æű
    0.09
    atics
    0.09
    Activations Density 0.015%

    No Known Activations